System and method for improving shooting accuracy and predicting shooting hit rate

This application claims priority from Korean Patent Application No. 10-2023-0027653 filed on Mar. 2, 2023 in the Korean Intellectual Property Office, and all the benefits accruing therefrom under 35 U.S.C. 119, the contents of which in its entirety are herein incorporated by reference.

The disclosure relates to a system and method for improving shooting accuracy and predicting shooting hit rate. The system and method for improving shooting accuracy and predicting shooting hit rate can improve shooting accuracy by executing a learning algorithm using shooting data and shooting result data from at least one shooting system, and predict the shooting hit rate of a shooting event in a current surrounding environment and provide the results of the prediction to an operator.

The shooting hit rate for turrets, mounted firearms, or other fire weapon systems (or shooting systems) is provided to the users. In such a fire weapon system, shots are based on a firing table, with the first shot being fired accordingly. After the firing of the first shot, subsequent shots are fired in a manner that reflects adjustments based on the measured distance between the target point and the point of impact of the first shot.

However, after the first shot, the shooting hit rate may significantly decrease due to enemy responses, and even though the shooting parameters and adjustments are automatically determined by the automatic fire control device, the hit rate of the firearm is still not high.

Conventionally, while the shooting hit rate for turrets, mounted firearms, or fire weapon systems (or shooting equipment) is provided to the users, there is no proper technology to improve shooting accuracy according to the current situation, or predict and provide shooting hit rate suitable for the current situation.

Therefore, there is a demand for a system and method that can learn and improve the shooting accuracy of a shooting system in real-time and simultaneously predict and provide the shooting hit rate to an operator.

To address the aforementioned problem, provided is a system and method for improving shooting accuracy and predicting shooting hit rate for a shooting system such as, but not limited to, a mobile remote weaponry, which can conduct learning through real-time shooting input and shooting result data and can enhance shooting accuracy by transmitting learned shooting results to the shooting system to correct ballistic values.

To address the aforementioned problem, provided is a system and method for improving shooting accuracy and predicting shooting hit rate, which can improve shooting accuracy in real time and on a real-time movement path, predict shooting hit rate in a current situation and on the real-time movement path, providing the results of the prediction to an operator, and learn and improve the shooting accuracy of a shooting system.

Additional aspects will be set forth in part in the description which follows and, in part, will be apparent from the description, or may be learned by practice of the presented embodiments.

According to an aspect of the disclosure, a system includes: a shooting system which may include at least one first processor which may be configured to: receive shooting ballistics-related data and shooting result data in real time; and detect real-time surrounding data, and an integrated computer which may include at least one second processor which may be configured to: receive the shooting ballistics-related data and the shooting result data from the shooting system; derive learning result data based on the shooting ballistics-related data and the shooting result data; and transmit the learning result data to the shooting system, wherein the at least one first processor may implement a neural network which may be configured to store and derive a shooting control data and a shooting prediction data and shooting prediction data based on the shooting ballistics-related data, the shooting result data, and the learning result data, wherein the at least one second processor may be further configured to update the learning result data based on the shooting ballistics-related data and the shooting result data received from the shooting system, wherein the at least one second processor may be further configured to transmit the updated learning result data to the shooting system, wherein the at least one first processor may be further configured to update the shooting ballistics-related data based on the updated learning result data received from the integrated computer, and wherein the at least one first processor may be further configured to update the shooting control data and the shooting prediction data of the neural network based on the updated learning result data received from the integrated computer.

The at least one second processor may be further configured to implement learning based on the shooting ballistics-related data and the shooting result data received from the shooting system, and the learning implemented by the at least one second processor may include shooting control learning for enhancing a shooting accuracy of the shooting system and a shooting prediction learning for enhancing a real-time shooting hit rate of the shooting system.

The shooting prediction learning of the shooting system may include a ballistic state of the shooting system and a posture status, position status, situation status, deployment status, and ballistic correction angle status of the at least one shooting system based on the real-time surrounding data.

The at least one first processor may be configured to increase the shooting accuracy toward a target point and predict the real-time shooting hit rate by updating the shooting ballistics-related data and the one shooting result data with the updated learning result data received from the integrated computer, and transmit, to an operator, a prediction value data based one the updated shooting ballistics-related data and the updated shooting result data.

The shooting system and the integrated computer may both include a shooting control algorithm and a shooting prediction algorithm, the receiving, transmitting, and updating of the shooting ballistics-related data, the shooting result data in real time, and the learning result data by the shooting system and the integrated computer is done in real time, the shooting control algorithm of the shooting system and the integrated computer may be configured to perform the shooting control learning based on the receiving, transmitting, and updating the shooting ballistics-related data, the shooting result data, and the learning result data in real time, and the shooting prediction algorithm of the shooting system and the integrated computer may be configured to perform the shooting prediction learning based on the receiving, transmitting, and updating the shooting ballistics-related data, the shooting result data, and the learning result data in real time.

The shooting control algorithm may include a shooting control local neural network part, which may be provided in the local neural network of the shooting system and to which the shooting control data is input, and a shooting control global neural network part, which may be provided in the global neural network of the integrated computer, may be configured to receive and learn from the shooting control data inputted to the shooting control local neural network part, and extract the learning result data, wherein the shooting control algorithm may be configured to update the shooting control data input to the shooting control global neural network part based on the learning result data and may be configured to reflect the updated shooting control data in real time.

The shooting system may be equipped with a driving part which may be configured to adjust the shooting of the shooting system, wherein the driving part may be configured to be operated and controlled based on the updated shooting control data of the shooting control local neural network part and ballistic correction angle status of the shooting system, and wherein the shooting system may be adjusted toward the target point according to the operation of the driving part.

The shooting control data input to the shooting control local neural network part may include at least one of tracking image data, raw data from among the tracking image data, distance data, ballistic correction angle data, N-axis motor position data, navigational data, gyro data, or ground surface condition information, wherein the shooting control local neural network part may be configured to transmit the shooting control data, wherein the shooting control global neural network part may include a glob input layer which may be configured to receive the raw data from the shooting control local neural network part, at least one global hidden layer, which may be connected to the global input layer through a plurality of neural networks, and a global output layer, which may be connected to the at least one global hidden layer through the plurality of neural networks, which may be configured to learn the learning result data through the at least one global hidden layer and output the learning result data to the at least one first processor, and wherein the at least one first processor may be configured to download the learning result data from the global output layer and update the learning result data as the raw data.

The shooting prediction algorithm may include a shooting prediction local neural network part, which may be provided in the local neural network of the shooting system and to which the shooting prediction data is input, and a shooting prediction global neural network part, which may be provided in the global neural network of the integrated computer, which may be configured to receive and learn from the shooting prediction data input to the shooting prediction local neural network part, and extract the learning result data, the shooting prediction algorithm may be configured to update the shooting prediction data input to the shooting prediction global neural network part based on the learning result data and may be configured to reflect the updated shooting prediction data in real time.

The shooting prediction data input to the shooting prediction local neural network part may include at least one of tracking image data, raw data from among tracking image data, distance data, ballistic correction angle data, N-axis motor position data, navigational data, gyro data, or ground surface condition information, the shooting prediction local neural network part may be configured to transmit the shooting prediction data, the shooting prediction global neural network part may include a global input layer which may be configured to receive the raw data from the shooting prediction local neural network part and store the received raw data, at least one global hidden layer, which may be connected to the global input layer through a plurality of neural networks, and a global output layer, which may be connected to the at least one global hidden layer through the plurality of neural networks, which may be configured to learn the learning result data, which is based on the raw data, through the at least one global hidden layer and output the learned learning result data, wherein the at least one first processor may be configured to download the learning result data which is output from the global output layer and update the learning result data output as the raw data.

The shooting system may further include a Light Detection and Ranging (LiDAR) sensor and an environmental sensor, which both may be configured to detect surrounding environment data of the shooting system.

The at least one second processor may be configured to implement a map data generation unit which may be configured to receive the surrounding environment data from the LiDAR sensor and generate surrounding environment information that ranges up to a target point, and a movement path analysis unit which may be configured to generate and analyze at least one movement path of the at least one shooting system to the target point based on the generated surrounding environment information generated by the map data generation unit.

The at least one first processor may be configured to transmit the surrounding environment data and a position information about the shooting system to the integrated computer, the at least one second processor may be further configured to generate at least one path for the map data generation unit for the shooting system and the surrounding environment of the target point, and the movement path analysis unit may be configured to analyze the at least one movement path for shooting system and analyze an optimal shooting position based on the learning result data received from the shooting system.

The at least one second processor may be further configured to implement a map generation unit which may be configured to generate the at least one movement path between the shooting system and a target point, and the at least one movement path may include at least one of shooting position information, terrain information, predicted shooting hit rate information, or estimated travel time to the target point based on whether the shooting system is moving or stationary.

According to an embodiment of the disclosure, a method of improving a shooting accuracy and predicting a shooting hit rate may include: receiving a target point; receiving, by a shooting system, data for shooting at the target point; transmitting the data for shooting at the target point received by the shooting system to an integrated computer; deriving, by the integrated computer, a learning result data for shooting control and shooting prediction by learning the data for shooting at the target point transmitted to the integrated computer; transmitting the learning result data from the integrated computer to shooting system; and updating, by the shooting system, the data for shooting at the target point transmitted by the shooting system based on the learning result data and reflecting the updated data for shooting at the target point in the shooting system in real time.

The method may further include, after the receiving the target point, collecting, by a Light Detection and Ranging (LiDAR) sensor of the shooting system, surrounding environment data for a current position of the shooting system and generating, by the integrated computer and based on the surrounding environment data, at least one movement path for the at least one shooting system and analyzing the at least one movement path to the target point.

The method may further include, after the updating the data for shooting at the target point transmitted by the shooting system and the reflecting the updated data for shooting at the target point in the shooting system in real time, displaying, on the at least one movement path, at least one of shooting position information, terrain information, predicted shooting hit rate information, or estimated travel time to the target point based on whether the shooting system is moving or stationary.

The method may further include receiving shooting result data by the shooting system, transmitting the shooting result data to the integrated computer, deriving, by the integrated computer, the learning result data for shooting control and shooting prediction by learning the shooting result data transmitted to the integrated computer, transmitting the learning result data based one the shooting result data from the integrated computer to the shooting system, and updating, by the shooting system, the data for shooting at the target point transmitted by the shooting system based on the learning result data learned from the shooting result data, and reflecting the updated data in the shooting system in real time.

The learning result data for shooting control and shooting prediction may include at least one of tracking image data, raw data from among the tracking image data, distance data, ballistic correction angle data, N-axis motor position data, navigational data, gyro data, or ground surface condition information.

The method may further include detecting real-time surrounding data, the data and the shooting result data may each include a ballistic state of the shooting system and a posture status, position status, situation status, deployment status, and ballistic correction angle status of the shooting system based on the real-time surrounding data.

Hereinafter, example embodiments of the disclosure will be described in detail with reference to the accompanying drawings. The same reference numerals are used for the same components in the drawings, and redundant descriptions thereof will be omitted. The embodiments described herein are example embodiments, and thus, the disclosure is not limited thereto and may be realized in various other forms. It is to be understood that singular forms include plural referents unless the context clearly dictates otherwise. The terms including technical or scientific terms used in the disclosure may have the same meanings as generally understood by those skilled in the art.

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present application, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

Terms used herein are for illustrating the embodiments rather than limiting the present disclosure. As used herein, the singular forms are intended to include plural forms as well, unless the context clearly indicates otherwise. Throughout this specification, the word “comprise” and variations such as “comprises” or “comprising,” will be understood to imply the inclusion of stated elements but not the exclusion of any other elements.

Hereinafter, one or more embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

An apparatus and method for improving shooting accuracy according to embodiments of the present disclosure will hereinafter be described with reference to the accompanying drawings.

1 FIG. 100 is a diagram illustrating a systemfor improving shooting accuracy and predicting shooting hit rate according to one or more embodiments.

1 FIG. 2 FIG.A 100 110 120 100 130 100 110 110 110 1121 1122 121 122 Referring to, the systemmay include one or more shooting systemsand an integrated computer. As will be described, the systemmay include a data algorithm(see) to enhance shooting accuracy and the prediction of shooting hit rate. Additionally, the systemmay include configurations for securing information on shooting hit rate at a particular position on a movement path between the position of the shooting systemsand a target point. The information on shooting hit rate at a particular position on a movement path between the position of the shooting systemsand a target point, for whether the shooting systemsare stationary or moving, may be obtained by a Light Detection and Ranging (LiDAR) sensor, an environmental sensor, a map data generation unit, and a movement path analysis unit.

100 100 The systemmay include a display module which may visually provide information to the outside (e.g., a user) of the system. The display module may include a display, a hologram device, or a projector and control circuitry to control a corresponding one of the display, hologram device, and projector. The display module may include touch circuitry (e.g., a touch sensor) adapted to detect a touch, or sensor circuitry (e.g., a pressure sensor) adapted to measure the intensity of force incurred by the touch.

100 120 110 100 According to one or more embodiments, the systemis configured to allow the integrated computerto execute a learning algorithm using data related to the surrounding environment (i.e. real time surrounding data) of the shooting systemsand at least one shooting ballistics data and shooting results data. To provide an improved shooting accuracy and shooting hit rate to an operator, the systemis further configured to continuously update learned data through the learning algorithm, enhance (or raise) shooting accuracy, and predict the shooting hit rate suitable for a current situation (i.e. prediction value data).

120 110 110 1 2 120 The integrated computer, which controls the shooting systems, progresses with learning. The shooting devices (e.g., a remote armament device) equipped in the shooting systemsuse learning result data (i.e., learning results Rand R) from the integrated computerso that as learning progresses, shooting accuracy improves over time and a higher shooting hit rate is secured.

110 110 110 100 110 a n One or more shooting systems, e.g., shooting systemsthrough, may be provided in the system. Each of the shooting systemsmay be configured to receive at least one shooting ballistics data, receive real-time shooting result data in real time, and detect real-time surroundings data.

110 110 110 120 120 110 110 120 110 110 110 110 115 115 119 117 110 117 The more shooting systemsthere are, the more data can be secured from the shooting systems. The more data secured from the shooting systems, the more data can be transmitted to the integrated computer, which will be described later. The integrated computermay perform its own learning process by integrating received (or downloaded) data, and learning result data may be transmitted (or downloaded) back to the shooting systems. The shooting systemsare updated with data received (or downloaded) from the integrated computer. As the shooting systemsare updated, the shooting accuracy of the shooting systemscan be improved, and the shooting hit rate of the shooting systemscan be predicted more accurately. As described later, each of the shooting systemsmay be equipped with a local neural network partfor shooting control and prediction. Result data from the local neural network partmay be used to output a current hit rate(i.e. current shooting hit rate) and data for the operation of a driving partof the remote armament device of each of the shooting systems. The driving partmay include at least one of a hydraulic actuator, a hydraulic motor or an electric motor, not being limited thereto.

120 110 110 110 120 110 110 110 120 110 120 1 2 110 110 120 120 110 a n a n According to one or more embodiments, the integrated computermay be configured to control one or more shooting systems(e.g. shooting systemsthrough). The integrated computeris configured to transmit data to and receive data from the shooting systems, particularly, shooting systemsthrough. The integrated computerreceives data from the shooting systemsand conducts learning based on the received data. The integrated computermay transmit learning result data results (i.e., the learning results Rand R) to the shooting systems. The shooting systemsmay implement updates by reflecting the learning data results received from the integrated computerin their respective data. The integrated computermay be configured to learn on its own from data transmitted from the shooting systems, specifically shooting ballistics-related data and shooting result data, as well as various terrain and surrounding environment data.

120 125 110 125 110 1 2 1 2 120 115 110 1 2 115 110 1 2 115 115 110 110 As will be described, the integrated computermay be equipped with a global neural network part, which learns shooting control and prediction from the data received from the shooting systems. The global neural network partmay learn from the data received from at least one shooting systemand derive the learning result data (i.e., the learning results Rand R). The learning results Rand Rfor shooting control and prediction, derived from the integrated computer, are downloaded (or transmitted) to the local neural network partsof the shooting systems. The downloaded learning results Rand Rare reflected into the local neural network partsof the shooting systems. From the downloaded learning results Rand R, data values of the local neural network partsare updated so that shooting ballistics-related data may be updated to the latest version. Result values output from the local neural network partsthat have been updated are reflected in the remote armament devices of the shooting systems. As a result, both the real-time shooting accuracy of the shooting systemstoward each target and the accuracy of predicted shooting hit rates can be enhanced, and such predicted shooting accuracies and shooting hit rates can be configured to the operator.

110 120 According to one or more embodiments, each of the shooting systemsand the integrated computermay be physically implemented as one or more processors such as a central processing unit (CPU), an application processor unit (APU), a graphics processing unit (GPU), a neural processing unit (NPU), an image signal processor (ISP), a sensor hub processor, or a communication processor (CP), and a hardware accelerator configured to perform functions and operations described by software or software module stored in one or more memories included therein or an external memory device.

The memory may store various data used by the processors. The various data may include software and input data or output data for a command related thereto. The memory may include the volatile memory or the non-volatile memory or both volatile memory and the non-volatile memory.

The program may be stored in the memory as software, and may include an operating system (OS), middleware, and/or an application.

120 As mentioned above, the integrated computermay derive the learning result data for shooting control and prediction through its own learning process.

120 110 110 120 110 110 120 110 According to one or more embodiments, the integrated computermay be configured to acquire information on the current position of the shooting systemsand the target point which may include map data of the current position of the shooting systemsand map data of the surroundings of the target point. The integrated computermay be configured to analyze the surrounding environment of the shooting systemsand the target point. Through the map data and the results of the analysis of the surrounding environment of the shooting systemsand the target point, the integrated computermay be configured to create a movement path between the position of the shooting systemsand the target point, calculate information on each region on the movement path and suitable shooting positions, and calculate shooting hit rate.

2 FIG.A 130 100 is a schematic diagram illustrating the data algorithmof the systemaccording to one or more embodiments.

2 FIG.B 130 100 is a configuration view illustrating an operation of the data algorithmof the systemaccording to one or more embodiments.

2 2 FIGS.A andB 100 130 120 110 Referring to, the systemmay include the data algorithm, which is for enhancing shooting accuracy and predicting shooting hit rate between the integrated computerand each of the shooting systems.

130 120 110 120 110 The data algorithmmay be provided in both the integrated computerand each of the shooting systemsto enable data to be transmitted (or downloaded) between the integrated computerand each of the shooting systems.

130 The data algorithmmay be classified into two types.

130 115 125 130 131 132 132 First, the data algorithmmay be configured as a local neural network partor a global neural network partdepending on its installation position and whether learning is implemented. Second, the data algorithmmay be configured as a shooting control algorithm(i.e. shooting control learning algorithm) for improving shooting accuracy through shooting control or a shooting prediction algorithm(i.e. shooting prediction learning algorithm) for predicting shooting hit rate. The shooting prediction learning algorithmmay include shooting prediction data.

130 131 132 131 132 a a b b. Due to these two classification types, the data algorithmmay include a shooting control local neural network part, a shooting prediction local neural network part, a shooting control global neural network part, and a shooting prediction global neural network part

115 110 115 115 115 115 1151 1152 110 120 115 1151 1152 1151 1152 1151 1152 1151 1152 115 115 1151 1152 1151 1152 1151 1152 a a b b a a c c b b a a b b c c. The local neural network partmay be provided in each of the shooting systems. Although the local neural network partdoes not perform its own learning process, the local neural network partis an algorithm that can derive shooting control and prediction results from input data. The local neural network partmay be considered an algorithm for storing input data and driving a shooting based on the input data. The local neural network partmay include local input layersand, which receive data input from each of the shooting systemsor data updated through the integrated computer. The local neural network partmay include a plurality of local hidden layersand, which are connected to the local input layersandthrough a plurality of neural networks, and a local output layerand, which is connected to the local hidden layerandthrough a plurality of neural networks. Therefore, the local neural network partmay be considered an algorithm that extracts driving values for real-time shooting control for the target point. The local neural network partmay also be considered an algorithm that predicts a current shooting hit rate through the neural network connections of the local input layersand, the local hidden layersand, and the local output layerand

125 120 125 125 1251 1252 110 1251 1252 1251 1252 1251 1252 1251 1252 a a b b a a c c b b The global neural network partmay be provided in the integrated computer. The global neural network partis a learning algorithm that performs its own learning process. The global neural network partmay include a global input layerand, which receives data from each of the shooting systemsfor its self-learning, at least one global hidden layerand, which is connected to the global input layerandthrough a plurality of neural networks to perform learning, and a global output layerand, which is connected to the at least one global hidden layerandthrough neural networks to output learning results and through the integration and learning of data for accuracy.

125 110 125 1251 1252 1251 1252 125 110 a a c c The global neural network partderives learning results regarding the shooting accuracy and shooting hit rate of each of the shooting systemsfrom the integration and learning of data and through the global neural network part'slayers ranging from the global input layerandto the global output layerand. Learning result data (also referred to as weight values) derived from the global neural network partmay be transmitted and downloaded to each of the shooting systems.

131 132 115 125 120 The shooting control algorithmand the shooting prediction algorithmmay be considered as algorithms for allowing the local neural network partand the global neural network partof the integrated computerto download data from each other in real time, for improving shooting accuracy through shooting control, and for predicting shooting hit rate.

131 132 110 Data learned through the shooting control algorithmand the shooting prediction algorithmmay be reflected in real-time shooting of each of the shooting systems.

131 131 131 a b. The shooting control learning algorithmmay include a shooting control local neural network partand a shooting control global neural network part

131 110 131 a a. The shooting control local neural network partmay be provided in each of the shooting systems, and data for shooting control may be input to the shooting control local neural network part

131 120 131 131 1 2 b a b The shooting control global neural network partmay be provided in the integrated computerand may be configured to receive data from the shooting control local neural network partfor learning. The shooting control global neural network partmay be configured to extract the learning result data Rand R.

131 110 Data learned and updated through the shooting control algorithmmay be reflected in each of the shooting systems, which enables the update of the corresponding data and thereby enhancing shooting accuracy.

131 131 120 131 110 Specifically, the shooting control algorithmmay receive at least one shooting ballistics-related data including tracking image data, raw data among the tracking image data, distance data, ballistic correction angle data, N-axis motor position data, navigation data, gyro data, and ground surface condition information. The shooting control algorithmreceives both shooting ballistics-related data and updated data from the integrated computer, which allows real-time updating of each data to the latest version. The shooting control algorithmmay learn from current input information in the case of both successful and failed shootings conducted by each of the shooting systems.

110 120 130 110 110 110 120 120 110 Additionally, the more the input data and shooting result data is from each of the shooting systems, the higher the learning and accuracy of the integrated computercan be. It may be difficult to conduct the learning algorithmas many times (e.g., tens of thousands of times) as desired through shooting in each of the shooting systems. However, if data from at least one shooting systems(particularly, from a plurality of shooting systems) is transmitted to the integrated computer, the integrated computermay perform learning based on the data received from each of the shooting systems.

120 120 131 120 131 110 131 110 b a a As mentioned above, when input data (including shooting ballistics data) for shootings and shooting result data after shooting are transmitted to the integrated computer, the integrated computerperforms learning through the shooting control global neural network part. Learning result data learned from the integrated computermay be transmitted to the shooting control local neural network partof each of the shooting systems. Data in the shooting control local neural network partis updated through received data, and as a result, the shooting accuracy of each of the shooting systemsmay be improved in real time.

132 130 110 110 110 Data learned and updated through the shooting prediction learning algorithmof the data algorithmmay be reflected each of the shooting systems, which enables the prediction of the shooting hit rate of each of the shooting systemsbased on the posture, position, situation, and state of each of the shooting systems.

132 132 132 a b. According to one or more embodiments, the shooting prediction algorithmmay include a shooting prediction local neural network partand a shooting prediction global neural network part

132 110 132 a a. The shooting prediction local neural network partmay be provided in the shooting systems, and data for shooting prediction may be input to the shooting prediction local neural network part

132 120 132 132 b b a The shooting prediction global neural network partmay be provided in the integrated computer. The shooting prediction global neural network partmay receive data from the shooting prediction local neural network part, perform learning, and extract learning result data.

132 110 Data learned and updated through the shooting prediction algorithmmay be reflected in each of the shooting systems, which enables the update of corresponding data and thus facilitates the prediction of shooting hit rate.

132 132 120 132 110 132 110 110 According to one or more embodiments, the shooting prediction algorithmmay receive at least one shooting ballistics-related data from one or more of tracking image data, distance data, ballistic correction angles, N-axis motor position data, navigation data, gyro data, and surface condition information. The shooting prediction algorithmmay also receive updated data from the integrated computer, enabling the real-time update of each data to the latest version. The shooting prediction algorithmmay learn from current input information in the case of both successful shootings and failed shootings conducted by each of the shooting systems. As a result of this learning, the shooting prediction algorithmmay predict the shooting hit rate of each of the shooting systemsbased on the posture, position, situation, and status of each of the shooting systems.

130 110 110 110 120 120 110 132 110 110 110 It may be difficult to conduct learning by executing the learning algorithmas many times (e.g., tens of thousands of times) as desired through shooting in each of the shooting systems. However, if data from at least one shooting systems(particularly, from a plurality of shooting systems) is transmitted to the integrated computer, the integrated computercan perform learning based on the data received from each of the shooting systems. Moreover, the shooting prediction algorithmcan predict the shooting hit rate of each of the shooting systemsbased on the posture, position, situation, and status of each of the shooting systems. Each of the shooting systemsmay include a ballistic state, a posture status, position status, situation status, deployment status, and ballistic correction angle status. All of which may be based on the real-time surrounding data.

110 132 120 132 132 110 120 132 120 132 1 2 132 110 1 2 132 110 100 110 a b a b a b b According to one or more embodiments, each of the shooting systemsis equipped with the shooting prediction local neural network part, and the integrated computeris equipped with the shooting prediction global neural network part. Thus, when the shooting prediction local neural network partin each of the shooting systemssends shooting result data to the integrated computer, the shooting prediction global neural network partin the integrated computerperforms learning based on the data sent from the shooting prediction local neural network part. The learning result data Rand Rgenerated by the shooting prediction global neural network partare then transmitted back to each of the shooting systems. The learning result data Rand Rgenerated by the shooting prediction global neural network partmay be updated data values. At a particular point upon completion of learning, the shooting systemscan predict the shooting hit rate of each shooting systemin the current situation under the current conditions and can provide the results of the prediction to the operator of each of the shooting systems.

3 FIG. 121 122 112 is a schematic configuration view illustrating generation of surrounding environment information by a map data generation unitand generation and analysis of a movement path by a movement path analysis unitthrough a sensoraccording to one or more embodiments.

3 FIG. 110 112 110 112 1121 1122 120 121 1121 1122 122 121 Referring to, the shooting systemsmay be equipped with the sensor, which detects a surrounding environment of the shooting systems. The sensormay include a light detection and ranging (LiDAR) sensorand an environmental sensorwhich may include at least one of camera, temperature sensor, humidity sensor, or so on. The integrated computermay also include the map data generation unit, which receives information from the LiDAR sensorand the environmental sensorto generate surrounding environment information ranging up to a target and a movement path analysis unit, and generate and analyze a movement path to a target point based on the surrounding environment information generated by the map data generation unit.

110 1121 1122 110 120 121 110 122 110 110 Surrounding environment data of the shooting systems, detected by the LiDAR sensorand the environmental sensor, and the position information about the shooting systemsare transmitted to the integrated computerto generate the surrounding environment information by the map data generation unitfor the shooting systemsand the target point. Moreover, the path analysis unitmay analyze an optimal shooting position and the movement path for the shooting systemby performing learning of data transmitted from the shooting systems.

121 110 121 110 In the map data generation unit, at least one movement path between the shooting systemsand the target point may be generated and displayed. For this purpose, the map data generation unitmay include a display module or connected to the display module. At least one information from among shooting position information, terrain information, predicted shooting hit rate information, and estimated travel time to the target point for whether the shooting systemsare moving or stationary may be displayed on the movement path.

110 1121 1122 1121 1122 120 110 120 110 110 According to one or more embodiments, a plurality of shooting systemsthat are configured to be movable are equipped with the LiDAR sensorand the environmental sensor. Surrounding environment data input to the LiDAR sensorand the environmental sensor, such as topographical features and ground surface information, may be transmitted to the integrated computer, together with current position information of the shooting systems. The integrated computermay analyze the surrounding environment data received from the shooting systemsand may generate the surrounding environment information based on the results of the analysis. The surrounding environment information may be used to find an optimal shooting position through the analysis of the movement path during the movement of the shooting systems.

4 FIG.A 4 FIG.B 4 FIG.C 5 FIG. 130 121 122 100 120 100 110 120 100 125 115 121 110 is a schematic configuration view illustrating how to predict a shooting accuracy and a shooting hit rate at a fixed or moving position through the data algorithm, the map data generation unit, and the movement path analysis unitof the systemaccording to one or more embodiments.is a drawing illustrating how the integrated computerof the systempredicts shooting hit rate at a fixed or moving position of each of the shooting systemsaccording to one or more embodiments.is a drawing illustrating how the integrated computerof the systemderives result data using the global neural network partand the local neural network partaccording to one or more embodiments.is a drawing illustrating how to display a movement path in the map data generation unitand a predicted shooting hit rate and terrain information for each of the shooting systemsat a shooting position according to one or more embodiment.

4 5 FIGS.A through 3 FIG. 110 120 110 132 1 121 132 120 132 120 132 132 132 132 110 110 121 110 a b a a b a Referring to, the target point may be determined to initiate shooting. Once the target point is determined, each of the shooting systemsmay perform shooting prediction and the generation of a movement path for shooting aimed at the target point or for moving to the target point. According to one or more embodiments and with reference to, the integrated computermay generate at least one movement path for each of the shooting systemsthrough real-time input and the stored surrounding environment information. Also, data is input, learned, and transmitted for updates through the shooting prediction algorithm. For pathsthrough n generated by the map data generation unit, position data for each position and at least one corresponding shooting ballistics-related virtual data may be input to the shooting prediction local neural network part. These input data may be transmitted to the integrated computer. The shooting prediction global neural network partperforms learning of the data received from the integrated computerand transmits the results of the learning back to the shooting prediction local neural network part. The shooting prediction local neural network partupdates data with the result data received from the shooting prediction global neural network part. Then, the shooting prediction local neural network partimproves the shooting accuracy of each of the shooting systemsand predicts the shooting hit rate of each shooting systemusing the latest updated data. Additionally, prediction results may be displayed at corresponding position points in the map data generation unit, and for particular position points, information indicating whether the positions are with clear sightlines, predicted higher hit rates expected due to the roads being flat or with high ground advantageous for shooting, may be marked on the map and may be transmitted and displayed to be identified by the operator of each of the shooting systems.

110 110 121 122 110 110 121 In a case where a direct-fire M shooting systemand an indirect-fire M shooting systemmoves to the target point and performs shooting at the target point, the map data generation unitgenerates a map up to the target point, the movement path analysis unitanalyzes the movement paths for both the direct-fire M shooting systemand the indirect-fire M shooting system, and the generated paths may be displayed in the map data generation unit.

110 110 130 121 121 110 110 Furthermore, for selected or input position points or analyzed position points along the movement paths for the direct-fire M shooting systemand the indirect-fire M shooting systemmay result data such as travel time, terrain information, and shooting hit rates, derived through analysis by the data algorithmand the map data generation unit. The result data may be displayed in the map data generation unitto be identified by the operators of the direct-fire M shooting systemand the indirect-fire M shooting system.

120 110 132 110 121 121 110 121 110 a As mentioned earlier, the integrated computermay generate, and display on the display module, a movement path between the position of each of the shooting systemsand the target point and calculate one or more areas (i.e. terrains) on the movement path, such as a flat terrain A, a high terrain B, a downhill terrain C, and a hidden terrain D. The shooting prediction local neural network partmay learn shooting hit rates for the terrains A, B, C, and D, upgrade the corresponding data, transmit the results of the calculation to the operator of each of the shooting systems, and display the results of the calculation in the map data generation unit. Shooting hit rates may be predicted as the percentage of how often the target point may be shot, for example, the shooting hit rates may be predicted to be 85%, 75%, 65%, and 80% for the terrains A, B, C, and D, respectively. The map data generation unitmay be shared with the operator of each of the shooting systems, and such shared data may be displayed in the map data generation unit, showing the calculated shooting hit rates and terrain information for the respective positions for the operator of each of the shooting systemsto verify.

6 FIG. is a schematic flowchart illustrating a method of improving shooting accuracy according to an one or more embodiments.

6 FIG. 10 110 20 120 30 40 110 50 60 Referring to, the method of improving shooting accuracy according to one or more embodiments may include the steps of: receiving a target point (S), inputting input data and shooting result data to each of the shooting systems(S), transferring data to the integrated computer(S), implementing learning data (S), transmitting learning result data to each of the shooting systems(S), and performing an update (S).

10 Specifically, the target point may be received first (step S).

110 15 Thereafter, the surrounding environment information may be generated for each of the shooting systemsin relation to the target point (S) and displayed on the display module.

110 112 110 Surrounding environment data for the current position of each of the shooting systemsmay be collected through the LiDAR sensorof each of the shooting systemsas a surrounding environment data collection step.

110 120 15 After collecting the surrounding environment data, the surrounding environment information for each of the shooting systemsand a movement path to the target point may be generated in the integrated computer, using the surrounding environment data (S).

110 110 110 20 Upon receiving the target point, at least one data for shooting at the target point, such as, at least one shooting ballistics-related data, may be received from each of the shooting systems, and after shooting at the target point from each shooting system, the shooting result data may be received in real time from each of the shooting systems(S).

110 120 30 Thereafter, the input data and the shooting result data from each of the shooting systemsmay be transferred to the integrated computer(S).

120 131 132 40 b b Thereafter, the integrated computermay receive the input data and the shooting result data and store and learn the received data through the shooting control global neural network partand the shooting prediction global neural network part, thereby implementing learning data for shooting control and for shooting prediction (S).

120 110 50 Thereafter, the learning data of the integrated computermay be transmitted to each of the shooting systems(S).

110 110 60 Thereafter, data of each of the shooting systemsmay be updated, and the learning data may be reflected in each of the shooting systemsin real time (S).

110 121 70 Thereafter, at least one information from among shooting position information, terrain information, predicted shooting hit rate information, and estimated travel time to the target point for whether each of the shooting systemsis stationary or moving may be displayed in a location of at least one point on the movement path in the map data generation unit(S).

According to one or more embodiments, when input data for shootings conducted toward a shooting target point through multiple shooting systems and shooting result data regarding the conducted shootings are transmitted to an integrated computer, the integrated computer proceeds with learning through a global neural network part for shooting control, and transmits the results of the learning to the local neural network part so that the shooting accuracy of the shooting systems can be improved in real time by the local neural network part.

Furthermore, learning conducted through the global neural network part for shooting control allows for the prediction of the shooting hit rate in various conditions such as the posture, position, situation, and state of the shooting systems. Learning conducted through the global neural network part for shooting control enables the prediction of the shooting hit rate of the multiple shooting systems. Therefore, the operator can predict the shooting hit rate of a desired shooting system among the multiple shooting systems and choose a higher shooting accuracy based on the results of the prediction.

Additionally, information such as environmental data, terrain information, and shooting hit rates along the movement path of each operational shooting system to a target object can be predicted, and the operator can receive and identify the predicted information and can conduct optimal shooting based on the predicted information.

Moreover, data detected through a detection unit (such as a Light Detection and Ranging (LiDAR) sensor) including topographical features and ground surface information, is transmitted along with position information of each shooting system to the integrated computer. Then, the integrated computer generates map data through the detected data from the multiple shooting systems and provides an optimal shooting position through path analysis as each operational shooting systems moves.

The term “system,” “computer,” “network,” “network part,” and “layer” may include a unit implemented in hardware, software, or firmware, and may interchangeably be used with other terms, for example, “logic,” “block,” “part,” or “circuitry”. A system may be a single integral component, or a minimum unit or part thereof, adapted to perform one or more functions. According to one or more embodiments, the system may be implemented in a form of an application-specific integrated circuit (ASIC).

110 120 100 100 An embodiment as set forth herein may be implemented as software (e.g., the shooting systems, integrated computer) including one or more instructions that are stored in a storage medium (e.g., memory) that is readable by a machine (e.g., the system). According to one or more embodiments, a processor (e.g., the processor) of the machine (e.g., the system) may invoke at least one of the one or more instructions stored in the storage medium, and execute it, with or without using one or more other components under the control of the processor. This allows the machine to be operated to perform at least one function according to the at least one instruction invoked. The one or more instructions may include a code generated by a complier or a code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Wherein, the term “non-transitory” simply means that the storage medium is a tangible device, and does not include a signal (e.g., an electromagnetic wave), but this term does not differentiate between where data is semi-permanently stored in the storage medium and where the data is temporarily stored in the storage medium.

Each component (e.g., a shooting system) of the above-described components may include a single entity or multiple entities. One or more of the above-described components may be omitted, or one or more other components may be added. Alternatively or additionally, a plurality of components (e.g., the shooting systems) may be integrated into a single component. According to one or more embodiments, the integrated component may perform one or more functions of each of the plurality of components in the same or similar manner as they are performed by a corresponding one of the plurality of components before the integration.

According to one or more embodiments, operations performed by the module, the program, or another component may be carried out sequentially, in parallel, repeatedly, or heuristically, or one or more of the operations may be executed in a different order or omitted, or one or more other operations may be added.

While the disclosure has been illustrated and described with reference to one or more embodiments, it will be understood that the one or more embodiments are intended to be illustrative, not limiting. It will be further understood by those skilled in the art that various changes in form and detail may be made without departing from the true spirit and full scope of the disclosure, including the appended claims and their equivalents. It will also be understood that any of the embodiments described herein may be used in conjunction with any other embodiments described herein.